[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DKQ2B0SCQKS25EN2JF11SA":3,"skill-same:01M7DKQ2B0SCQKS25EN2JF11SA":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M7DKQ2B0SCQKS25EN2JF11SA","filter-escapers-with-mixscape",null,"Label and remove escaping cells in a pooled CRISPR screen with single-cell readout (Perturb-seq, CROP-seq) with Mixscape from pertpy, from a log-normalized AnnData with a guide or perturbation column and a non-targeting control to adata_mixscape.h5ad without the non-perturbed (NP) cells, plus the NP fraction of every perturbation. Use before per-perturbation differential expression when guide-assigned cells may have escaped knockout or knockdown and dilute the comparison, or when asked which cells of a screen were actually perturbed. Optional step with a heavy dependency; without pertpy the script exits cleanly and the DE runs on all guide-assigned cells.","lijinbio\u002Faiscientist-skills","lijinbio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16247242?v=4","01M7DKPQK7Q6V7QXAAPV51Z89N","Jin Li","01M7DKPQM0NMDN3M6XH7Z9AAKM",0,"MIT","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcrispr-screens\u002Ffilter-escapers-with-mixscape\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: filter-escapers-with-mixscape\ndescription: Label and remove escaping cells in a pooled CRISPR screen with single-cell readout (Perturb-seq, CROP-seq) with Mixscape from pertpy, from a log-normalized AnnData with a guide or perturbation column and a non-targeting control to adata_mixscape.h5ad without the non-perturbed (NP) cells, plus the NP fraction of every perturbation. Use before per-perturbation differential expression when guide-assigned cells may have escaped knockout or knockdown and dilute the comparison, or when asked which cells of a screen were actually perturbed. Optional step with a heavy dependency; without pertpy the script exits cleanly and the DE runs on all guide-assigned cells.\nlicense: MIT\ncompatibility: Python 3.12+ with scanpy, anndata and pertpy 1.4 (pip). No GPU, no scheduler. Without pertpy the script skips and exits 0.\nmetadata:\n  category: crispr-screens\n  version: \"1.0.0\"\n  status: community\n  author: \"Yijun Sun\"\n  aliases: \"mixscape_escape_filter\"\n  tags: \"crispr, perturb-seq, crop-seq, scrna-seq, mixscape, pertpy, escaping-cells\"\n  tested-with: \"pertpy 1.4.0, scanpy 1.12.1, anndata 0.12.16, pandas 2.3.3, numpy 2.4.6, scipy 1.17.1, scikit-learn 1.9.1, pynndescent 0.6.0, numba 0.68.0, Python 3.13.9\"\n  compute: \"1 CPU, 0.85 GB peak RAM, about 12 s for 240 cells x 47 genes (mostly pertpy import and JIT compilation)\"\n  requires-gpu: \"false\"\n  scheduler: \"none\"\n  requires-network: \"install\"\n  requires-secrets: \"none\"\n---\n\n# Remove escaping cells with Mixscape\n\nIn a real screen a fraction of the guide-assigned cells escape knockout or knockdown and look\ntranscriptionally like control. Keeping them dilutes every downstream comparison.\n`scripts\u002Freference.py` runs Mixscape (Papalexi et al., *Nat. Genetics* 2021, as implemented in\npertpy): it computes a local perturbation signature for every cell and classifies each cell as\nperturbed (KO), non-perturbed (NP, escaped) or control, then writes the AnnData without the NP\ncells for the per-perturbation DE (`compare-perturbations-to-control`).\n\nThis step is optional. pertpy is a heavy dependency and its Mixscape API drifts between versions.\nIf pertpy cannot be imported, the script prints a `SKIPPED` note and exits 0; the DE then runs on\nall guide-assigned cells, a conservative, effect-diluting choice that the report must state.\n\nThe most likely mistake is reading an NP fraction of 1.0 as \"every cell escaped\". Mixscape first\nlooks for genes that differ between the perturbation and the control; with fewer than 5 such\ngenes it labels the whole perturbation NP. A silent guide therefore loses all its cells here (the\ntests show it). That is \"no detectable signature\", the same result the E-distance ranking calls\nsilent, and it means the filtered file holds no cells of that perturbation.\n\nTested on synthetic data only (`tests\u002F`: 240 cells, 47 genes, a non-targeting control of 100\ncells; a knockout of 80 cells of which 40 lost the target and switched on a 5-gene program and 40\nescaped; and a silent guide of 60 cells) with pertpy 1.4.0, scanpy 1.12.1, anndata 0.12.16,\npandas 2.3.3, numpy 2.4.6, scipy 1.17.1, scikit-learn 1.9.1 and Python 3.13.9. Mixscape kept\nexactly the 40 knocked-out cells (NP fraction 0.5), removed all 60 cells of the silent guide and\nkept every control cell. The skip path is tested with pertpy made unimportable. No real-screen\nrun is recorded here.\n\n## 1. Environment setup\n\n```bash\nmamba create -y -n pertpy_1.4 -c conda-forge python=3.13 pip\nsource \"$(conda info --base)\u002Fetc\u002Fprofile.d\u002Fconda.sh\"\nconda activate pertpy_1.4\npip install scanpy==1.12.1 anndata==0.12.16 pandas==2.3.3 numpy==2.4.6 scipy==1.17.1 pertpy==1.4.0\npython -c \"import pertpy; print(pertpy.__version__)\"\n```\n\nThe `pip install` line is the one tested, in a plain Python 3.13.9 venv. The first\n`import pertpy` takes tens of seconds while it compiles; later imports take a few seconds.\n\nThe call to `ms.mixscape` passes the label column and the control by position because pertpy 1.0\nand earlier name the label argument `labels` and pertpy 1.4 names it `pert_key`. If your pertpy\nrejects the call, read `help(pt.tl.Mixscape.mixscape)` and adapt that one line.\n\n## 2. Prepare inputs\n\n- An AnnData file with **log-normalized** expression in `X` (the signature averages control\n  neighbours with `expm1` and returns to `log1p`) and a guide or perturbation label per cell in an\n  `obs` column, including the non-targeting control. The script reads `adata_qc.h5ad` from\n  `$AISCIENTIST_WORK`, else the file named by `$AISCIENTIST_DATASET`.\n- The output goes to `$AISCIENTIST_WORK` as well; this script writes no tables.\n\nMixscape classifies within each level of the perturbation column, so give it the same level\n(guide or target gene) that the DE will use. Identify the column and the control level from the\ndata as for the DE step, and keep the control cells through QC.\n\n## 3. Configure\n\n| Variable | Meaning | Default |\n| --- | --- | --- |\n| `PERT_KEY` | the `obs` column naming the guide or perturbation | `perturbation` |\n| `CONTROL` | the shared non-targeting level of `PERT_KEY` | `NT` |\n\nThe Mixscape calls use pertpy's defaults. In pertpy 1.4.0 those are: the signature of a cell is\nits difference from the mean of its 20 nearest control cells, searched in the first 15 PCs\n(pertpy computes a PCA if `X_pca` is missing); a perturbation needs at least 5 genes with\nadjusted p \u003C 0.05 and |log fold change| ≥ 0.25 against control; and a cell with posterior above\n0.5 in the perturbed component is KO. To change them, add keyword arguments to the two calls:\n`perturbation_type=\"KD\"` labels CRISPRi cells KD instead of KO (the filter keeps both), and\n`split_by=\"\u003Ccolumn>\"` runs the steps within each replicate or lane (pertpy's own example uses\n`split_by=\"replicate\"`). Record any change in the report.\n\n## 4. Run\n\n```bash\nexport AISCIENTIST_WORK=\u002Fpath\u002Fto\u002Fwork\n# or, with no adata_qc.h5ad in the work directory:\nexport AISCIENTIST_DATASET=\u002Fpath\u002Fto\u002Fscreen.h5ad\npython scripts\u002Freference.py\n```\n\nIn AiScientist: read the file with `read_skill_reference`, set the values for this dataset, and\nrun it with `run_code`, which sets the variables.\n\n## 5. Validate before using the output\n\nThe JSON summary on stdout, and `$AISCIENTIST_WORK\u002Fadata_mixscape.h5ad` holding the kept cells\nwith `obs[\"mixscape_class\"]`, `obs[\"mixscape_class_global\"]` (KO, NP or the control label),\n`obs[\"mixscape_class_p_ko\"]` and the signature in `layers[\"X_pert\"]`.\n\n1. **`mixscape`**: `OK`, or `SKIPPED` with the reason. After a skip, the DE runs on all\n   guide-assigned cells: say so.\n2. **The control**: every control cell is kept; `class_counts` shows them under the control\n   label.\n3. **`np_fraction_by_perturbation`**: between 0 and 1 for a perturbation with a signature; a\n   high fraction means many escapers, or a weak guide. Exactly 1.0 means no signature (above);\n   cross-check with the E-distance ranking.\n4. **`n_cells_before` and `n_cells_after_removing_NP`**: every perturbation you will test still\n   has enough cells for the DE (`MIN_CELLS`, default 30).\n5. Point the DE at the filtered file: in `compare-perturbations-to-control`, change the checkpoint\n   line to read `adata_mixscape.h5ad`.\n\n## Report\n\nWhether Mixscape ran (with the pertpy version) or was skipped and why; the perturbation column,\nthe control level and the level (guide or target); any argument changed from pertpy's defaults;\nthe NP fraction of every perturbation, with the perturbations labelled NP as a whole named as\nhaving no detectable signature; and the cells before and after. If it was skipped, state that\nthe DE used all guide-assigned cells and that effects may be diluted.\n","# Remove escaping cells with Mixscape\n\nIn a real screen a fraction of the guide-assigned cells escape knockout or knockdown and look\ntranscriptionally like control. Keeping them dilutes every downstream comparison.\n`scripts\u002Freference.py` runs Mixscape (Papalexi et al., *Nat. Genetics* 2021, as implemented in\npertpy): it computes a local perturbation signature for every cell and classifies each cell as\nperturbed (KO), non-perturbed (NP, escaped) or control, then writes the AnnData without the NP\ncells for the per-perturbation DE (`compare-perturbations-to-control`).\n\nThis step is optional. pertpy is a heavy dependency and its Mixscape API drifts between versions.\nIf pertpy cannot be imported, the script prints a `SKIPPED` note and exits 0; the DE then runs on\nall guide-assigned cells, a conservative, effect-diluting choice that the report must state.\n\nThe most likely mistake is reading an NP fraction of 1.0 as \"every cell escaped\". Mixscape first\nlooks for genes that differ between the perturbation and the control; with fewer than 5 such\ngenes it labels the whole perturbation NP. A silent guide therefore loses all its cells here (the\ntests show it). That is \"no detectable signature\", the same result the E-distance ranking calls\nsilent, and it means the filtered file holds no cells of that perturbation.\n\nTested on synthetic data only (`tests\u002F`: 240 cells, 47 genes, a non-targeting control of 100\ncells; a knockout of 80 cells of which 40 lost the target and switched on a 5-gene program and 40\nescaped; and a silent guide of 60 cells) with pertpy 1.4.0, scanpy 1.12.1, anndata 0.12.16,\npandas 2.3.3, numpy 2.4.6, scipy 1.17.1, scikit-learn 1.9.1 and Python 3.13.9. Mixscape kept\nexactly the 40 knocked-out cells (NP fraction 0.5), removed all 60 cells of the silent guide and\nkept every control cell. The skip path is tested with pertpy made unimportable. No real-screen\nrun is recorded here.\n\n## 1. Environment setup\n\n```bash\nmamba create -y -n pertpy_1.4 -c conda-forge python=3.13 pip\nsource \"$(conda info --base)\u002Fetc\u002Fprofile.d\u002Fconda.sh\"\nconda activate pertpy_1.4\npip install scanpy==1.12.1 anndata==0.12.16 pandas==2.3.3 numpy==2.4.6 scipy==1.17.1 pertpy==1.4.0\npython -c \"import pertpy; print(pertpy.__version__)\"\n```\n\nThe `pip install` line is the one tested, in a plain Python 3.13.9 venv. The first\n`import pertpy` takes tens of seconds while it compiles; later imports take a few seconds.\n\nThe call to `ms.mixscape` passes the label column and the control by position because pertpy 1.0\nand earlier name the label argument `labels` and pertpy 1.4 names it `pert_key`. If your pertpy\nrejects the call, read `help(pt.tl.Mixscape.mixscape)` and adapt that one line.\n\n## 2. Prepare inputs\n\n- An AnnData file with **log-normalized** expression in `X` (the signature averages control\n  neighbours with `expm1` and returns to `log1p`) and a guide or perturbation label per cell in an\n  `obs` column, including the non-targeting control. The script reads `adata_qc.h5ad` from\n  `$AISCIENTIST_WORK`, else the file named by `$AISCIENTIST_DATASET`.\n- The output goes to `$AISCIENTIST_WORK` as well; this script writes no tables.\n\nMixscape classifies within each level of the perturbation column, so give it the same level\n(guide or target gene) that the DE will use. Identify the column and the control level from the\ndata as for the DE step, and keep the control cells through QC.\n\n## 3. Configure\n\n| Variable | Meaning | Default |\n| --- | --- | --- |\n| `PERT_KEY` | the `obs` column naming the guide or perturbation | `perturbation` |\n| `CONTROL` | the shared non-targeting level of `PERT_KEY` | `NT` |\n\nThe Mixscape calls use pertpy's defaults. In pertpy 1.4.0 those are: the signature of a cell is\nits difference from the mean of its 20 nearest control cells, searched in the first 15 PCs\n(pertpy computes a PCA if `X_pca` is missing); a perturbation needs at least 5 genes with\nadjusted p \u003C 0.05 and |log fold change| ≥ 0.25 against control; and a cell with posterior above\n0.5 in the perturbed component is KO. To change them, add keyword arguments to the two calls:\n`perturbation_type=\"KD\"` labels CRISPRi cells KD instead of KO (the filter keeps both), and\n`split_by=\"\u003Ccolumn>\"` runs the steps within each replicate or lane (pertpy's own example uses\n`split_by=\"replicate\"`). Record any change in the report.\n\n## 4. Run\n\n```bash\nexport AISCIENTIST_WORK=\u002Fpath\u002Fto\u002Fwork\n# or, with no adata_qc.h5ad in the work directory:\nexport AISCIENTIST_DATASET=\u002Fpath\u002Fto\u002Fscreen.h5ad\npython scripts\u002Freference.py\n```\n\nIn AiScientist: read the file with `read_skill_reference`, set the values for this dataset, and\nrun it with `run_code`, which sets the variables.\n\n## 5. Validate before using the output\n\nThe JSON summary on stdout, and `$AISCIENTIST_WORK\u002Fadata_mixscape.h5ad` holding the kept cells\nwith `obs[\"mixscape_class\"]`, `obs[\"mixscape_class_global\"]` (KO, NP or the control label),\n`obs[\"mixscape_class_p_ko\"]` and the signature in `layers[\"X_pert\"]`.\n\n1. **`mixscape`**: `OK`, or `SKIPPED` with the reason. After a skip, the DE runs on all\n   guide-assigned cells: say so.\n2. **The control**: every control cell is kept; `class_counts` shows them under the control\n   label.\n3. **`np_fraction_by_perturbation`**: between 0 and 1 for a perturbation with a signature; a\n   high fraction means many escapers, or a weak guide. Exactly 1.0 means no signature (above);\n   cross-check with the E-distance ranking.\n4. **`n_cells_before` and `n_cells_after_removing_NP`**: every perturbation you will test still\n   has enough cells for the DE (`MIN_CELLS`, default 30).\n5. Point the DE at the filtered file: in `compare-perturbations-to-control`, change the checkpoint\n   line to read `adata_mixscape.h5ad`.\n\n## Report\n\nWhether Mixscape ran (with the pertpy version) or was skipped and why; the perturbation column,\nthe control level and the level (guide or target); any argument changed from pertpy's defaults;\nthe NP fraction of every perturbation, with the perturbations labelled NP as a whole named as\nhaving no detectable signature; and the cells before and after. If it was skipped, state that\nthe DE used all guide-assigned cells and that effects may be diluted.\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":36},{"tags":25,"author":26,"status":27,"aliases":28,"compute":29,"version":30,"category":31,"scheduler":32,"tested-with":33,"requires-gpu":34,"requires-network":35,"requires-secrets":32},"crispr, perturb-seq, crop-seq, scrna-seq, mixscape, pertpy, escaping-cells","Yijun Sun","community","mixscape_escape_filter","1 CPU, 0.85 GB peak RAM, about 12 s for 240 cells x 47 genes (mostly pertpy import and JIT compilation)","1.0.0","crispr-screens","none","pertpy 1.4.0, scanpy 1.12.1, anndata 0.12.16, pandas 2.3.3, numpy 2.4.6, scipy 1.17.1, scikit-learn 1.9.1, pynndescent 0.6.0, numba 0.68.0, Python 3.13.9","false","install","Python 3.12+ with scanpy, anndata and pertpy 1.4 (pip). No GPU, no scheduler. Without pertpy the script skips and exits 0.","main","5c42aa74b19348cb68aa35301eba042a737d94d4","skills\u002Fcrispr-screens\u002Ffilter-escapers-with-mixscape",2,"https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills","https:\u002F\u002Fgithub.com\u002Flijinbio","2026-11-14 05:44:08",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add lijinbio\u002Faiscientist-skills --skill filter-escapers-with-mixscape",{"tool":50,"command":51},"bunx","bunx skills add lijinbio\u002Faiscientist-skills --skill filter-escapers-with-mixscape",{"tool":53,"command":54},"pnpm","pnpm dlx skills add lijinbio\u002Faiscientist-skills --skill filter-escapers-with-mixscape","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcrispr-screens\u002Ffilter-escapers-with-mixscape\u002FSKILL.md",true,[58,64],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Freference.py","SCRIPT","脚本",3899,"https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcrispr-screens\u002Ffilter-escapers-with-mixscape\u002Fscripts\u002Freference.py",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"tests\u002Ftest_filter_escapers_with_mixscape.py",4189,"https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcrispr-screens\u002Ffilter-escapers-with-mixscape\u002Ftests\u002Ftest_filter_escapers_with_mixscape.py",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DKZPCPYM78N1R0MVAVVYKT","verb-object-with-tool","One or two sentences on what the skill does and when to use it. Name the tool, the input it takes and the output it produces, then list the situations that should trigger it (for example \"Use when setting up X, writing a Y config, or diagnosing a failed Z run\").","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Ftemplate\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DKZCJMFJJB9ZH9YGCSQHR5","write-variant-tables","Write the five standard variant-annotation result tables - consequence, impact and ClinVar-significance distributions, a ClinVar pathogenic and likely-pathogenic list, and a shortlist of rare, damaging variants not in ClinVar - plus a JSON summary, from an annotated per-variant TSV (VEP consequence and impact, SIFT, PolyPhen, max population AF, rsID, ClinVar significance), in pure Python without re-parsing the VCF or re-running VEP. Use when a study needs these tables with a different rarity cutoff, impact set or damaging-predictor rule, or when rebuilding them from an existing annotation table. In AiScientist, annotate_variants already writes the default tables, so use this only for a custom cut.","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvariants\u002Fwrite-variant-tables\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DKZ3R4E6JEJT3YB6AHXE60","rank-phenotype-differentials-with-mcp","Map clinical phenotype text to grounded HPO terms and rank a research differential through an already configured phenotype-diagnosis MCP service with LIRICAL and optional literature adjudication. Use for explicit service-based analysis while preserving negation, uncertainty and original probabilities; retain the established workflow when the service is unavailable.","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvariants\u002Frank-phenotype-differentials-with-mcp\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7DKYS9R4F5EPCMDHSH3TEZ7","qc-vcf-callset","Judge whether a germline VCF callset is trustworthy before interpreting any variant - Ti\u002FTv, Het\u002FHom, SNP, indel and multiallelic counts, sample count and genotype call rate from bcftools stats (falling back to cyvcf2, then to a plain-Python Ti\u002FTv scan) - and flag values outside the expected human WGS or WES ranges. Writes tables\u002Fvcf_qc_summary.csv and data\u002Fvcf_qc.json with a qc_flags list. Use when a VCF (one sample or a cohort) arrives for annotation or prioritization, when a Ti\u002FTv or Het\u002FHom value needs interpreting, or when deciding whether downstream variant tables must carry a low-confidence caveat.","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvariants\u002Fqc-vcf-callset\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7DKYDRBFTBS2J58QMB7SMHK","prioritize-clinical-variants","Rank annotated variants into research-triage tiers (ClinVar pathogenic, likely pathogenic, VUS favouring pathogenic, VUS, likely benign, benign) from ClinVar significance used verbatim, gnomAD allele frequency against a dominant or recessive disease-model cutoff and the ACMG BA1 5 percent rule, and in-silico predictors (SIFT, PolyPhen, REVEL, CADD, AlphaMissense) as supporting evidence only. Pure Python; reads a per-variant annotation TSV and writes a tier-sorted CSV with the evidence for each tier plus a JSON of tier counts. Use when a rare-variant list from VEP, ClinVar and gnomAD annotation must be ordered for review (which variants to look at first) or when choosing the disease model and cutoffs for that ordering. Research triage only, NOT a clinical ACMG\u002FAMP classification.","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvariants\u002Fprioritize-clinical-variants\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7DKY2XPCQ2S639KTPSAJ170","normalize-vcf-with-bcftools","Normalize a VCF with bcftools norm before annotation or ClinVar\u002FgnomAD matching - split multiallelic sites into biallelic records, atomize MNPs into SNPs, then left-align and trim indels against the reference FASTA of the same build - writing an indexed normalized.vcf.gz and a JSON of record counts before and after. Use when a VCF not known to be normalized (especially an indel-heavy one) will be matched against ClinVar, gnomAD or dbSNP, compared between callers or loaded into PLINK, or when a known pathogenic indel comes back as not in ClinVar. In AiScientist, the offline annotate_variants path already normalizes, so do not plan it as a separate step there.","https:\u002F\u002Fgithub.com\u002Flijinbio\u002Faiscientist-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvariants\u002Fnormalize-vcf-with-bcftools\u002FSKILL.md",[],[]]